基于改进MobileFaceNet的人脸识别方法北大核心

针对目前大多数人脸识别算法参数多、计算量大,难以部署到移动端和嵌入式设备中的问题,提出了一种基于改进MobileFaceNet的人脸识别方法。通过对MobileFaceNet模型结构的调整,将bottleneck模块优化为sandglass模块,改良深度卷积和逐点卷积的相对位置,适当增大sandglass模块的输出通道数,从而减少特征压缩时的信息丢失,增强人脸空间特征的提取。实验结果表明:改进后的方法在LFW测试数据集上准确率达99.15%,模型大小和计算量分别仅为原算法的61%和45%,验证了所提方法的有效性。     

一种基于FCOS神经网络的小建筑物目标检测方法北大核心

提出了一种基于FCOS神经网络的小建筑物目标检测算法,针对FCOS模型在特征提取阶段提取到的小建筑物目标特征较少问题,引入多尺度检测和可变形卷积方式,加强网络对小建筑物目标的特征提取能力,并通过改进后的SGE注意力机制降低特征图中的干扰噪声权重。改进后的网络可以提取到更多的小建筑物目标特征,对环境干扰噪声的鲁棒性更强。在自己搭建的数据集上进行了实验测试,结果表明,在相同环境下网络改进后建筑物的整体检测准确率提升了1.7%,其中对小建筑物目标提升了3.6%,减少了小建筑物目标漏检、误检的问题。     

一种基于抽取LMS的距离旁瓣抑制方法

在噪声雷达中，传统相关处理方法的距离旁瓣受到时宽带宽积的限制，在有限相关处理时间内得到的距离旁瓣较高，会造成微弱目标被强目标、杂波旁瓣淹没的现象。提出一种基于抽取最小均方（Least Mean Square,LMS）滤波的噪声雷达旁瓣抑制方法，将LMS滤波器的系数作为距离压缩结果，从而获取较低的距离旁瓣。对该方法的性能进行了理论分析，并通过数字仿真验证了算法的有效性和理论分析的正确性。     

Mutual information maximizing GAN inversion for real face with identity preservation

Recent generative adversarial networks (GANs) have yielded remarkable performance in face image synthesis. GAN inversion embeds an image into the latent space of a pretrained generator, enabling it to be used for real face manipulation. However, current inversion approaches for real faces suffer the dilemma of initialization collapse and identity loss. In this paper, we propose a hierarchical GAN inversion for real faces with identity preservation based on mutual information maximization. We first use a facial domain guaranteed initialization to avoid the initialization collapse. Furthermore, we prove that maximizing the mutual information between inverted faces and their identities is equivalent to minimizing the distance between identity features from inverted and original faces. Optimization for real face inversion with identity preservation is implemented on this mutual information-maximizing constraint. Extensive experimental results show that our approach outperforms state-of-the-art solutions for inverting and editing real faces, particularly in terms of face identity preservation.     

Multi-scale and multi-patch transformer for sandstorm image enhancement

Sandstorm is a meteorological phenomenon common in arid and semi-arid regions. A sandstorm can carry large volumes of sand unexpectedly, which leads to severe color deviations and significantly degraded visibility when an image is taken in such a scenario. However, existing image enhancement methods cannot enhance sandstorm images well due to the challenging degradations and the scarcity of sandstorm training data. In this paper, we propose a Transformer with rotary position embedding to perform sandstorm image enhancement via building multi-scale and multi-patch dependencies. Our key insights in this work are 1) a multi-scale Transformer can globally eliminate the color deviations of sandstorm images via aggregating global information, 2) a multi-patch Transformer can recover local details well via learning the spatial variant degradations, and 3) a U-shape Transformer with rotary position embedding as the core unit of multi-scale and multi-patch Transformer can effectively build the long-range dependencies. We also contribute a real-world Sandstorm Image Enhancement (SIE) dataset including 1,400 sandstorm images with different degrees of degradations and various scenes. Experiments performed on synthetic images and real-world sandstorm images demonstrate that our proposed method not only obtains visually pleasing results but also outperforms state-of-the-art methods qualitatively and quantitatively.     

碳中和背景下配电网差异化节能降耗潜力评估分

为了提高配电网差异化节能降耗效果，解决现有潜力评估方法存在的应用性能差的问题，提出碳中和背景下配电网差异化节能降耗潜力优化评估方法。根据配电网的空间结构，构建相应的等值电路模型。在该模型下，从设备损耗和运行附加损耗2个方面计算配电网的损耗量。根据损耗量计算结果，确定配电网差异化碳中和节能降耗方式。从静态和动态2个角度设置潜力评估指标，通过指标数据处理、指标权重求解等步骤，得出配电网差异化节能降耗潜力的综合量化评估结果。将设计潜力评估方法应用到配电网的差异化节能降耗改造工作中，能够有效降低配电网的实际线损量、降低区域损耗费用，并具有较高的应用价值。     

Double pyrovanadates CaMgV2O7: Formation mechanism,phase structure,and thermodynamic properties

A double pyrovanadate CaMgV₂O₇ sample was synthesized via a facile solid-state route under an air atmosphere. The nonequilibrium formation pathways of the CaMgV₂O₇ were investigated via powder X-ray diffraction. A multistep reactions path (metavanadates–pyrovanadates–double pyrovanadate CaMgV₂O₇) was proposed to describe the formation of the CaMgV₂O₇ considering the thermodynamic and kinetic factors. The cell unit parameters of the CaMgV₂O₇ sample indicated the crystallization according to a monoclinic system with space group P12/c1(14), and the lattice parameters of a = 6.756 Å, b = 14.495 Å, c = 11.253 Å, β = 99.12, and V = 108.806 Å³. X-ray photoelectron spectroscopy also confirmed the +5 oxidation state vanadium in CaMgV₂O₇. The endothermic effects at 1033 and 1143 K were related to the incongruent melting and liquidus temperatures of CaMgV₂O₇, respectively. The comprehensive thermodynamic properties of CaMgV₂O₇ were established in both low- and high-temperature regions, utilizing a physical property measurement system and multi-high-temperature calorimetry (96 lines). The heat capacity (200 J mol K⁻¹) and entropy (198 J mol K⁻¹) at 298.15 K were computed based on the low-temperature heat capacity values, and the enthalpy of formation at 298.15 K was also estimated. The fitted high-temperature capacity can be used to obtain the changes in the enthalpy, entropy, and Gibbs free energy. This study is part of building a reliable thermodynamic database of the CaO–MgO–V₂O₅ system.     

疫情下电磁场理论课程的网络教学

本文主要总结了新冠疫情期间作者的电磁场理论课程在线教学经验。对比分析了录播和直播的优缺点后,选择录播教学方式。基于超星网络教学平台,展示了录播网络教学的具体措施,包括网上答疑和学习效果检查以及在线批改作业等。给出了网络教学可以为线下教学继续使用的方法和手段,为疫情结束后的正常教学提供了新的网络教学补充措施。     

5G核心网业务模型的智能化预测研究

摘 要：核心网业务模型的建立是5G网络容量规划和网络建设的基础，通过现有方法得到的理论业务模型是静态不可变的且与实际网络存在偏离。为了克服现有5G核心网业务模型与现网模型适配性较差以及规划设备无法满足用户实际业务需求的问题，提出了一种长短期记忆（long short-term memory，LSTM）网络与卷积LSTM （convolution LSTM，ConvLSTM）网络双通道融合的 5G 核心网业务模型预测方法。该方法基于人工智能（artificial intelligence，AI）技术以实现高质量的核心网业务模型的智能预测，形成数据反馈闭环，实现网络自优化调整，助力网络智能化建设。     

基于卷积神经网络的5G蜂窝网络无线定位方法

5G蜂窝网络发展迅猛，其覆盖面积将逐渐增大，因此使用5G蜂窝网络进行定位是有研究潜力的研究方向。本文提出一种新的深度学习技术来实现高效、高精度和低占用的定位，以代替传统指纹定位过程中繁重的指纹库生成以及距离计算。该方法建立了一个特殊的卷积神经网络，并根据5G天线信号的接收信号强度指示、相位和到达角等特征量，选择合适的输入数据格式构造样本组建训练集，对该卷积神经网络进行训练。训练得到的卷积神经网络可以替代指纹定位中的庞大指纹库，非常有利于直接在5G移动设备端实现定位。虽然卷积神经网络在训练过程中需要大量时间，但在训练完毕后直接进行分类定位的速度非常快，可以保障定位实现的实时性。本文所实现的卷积神经网络权重与偏置所占内存不到0.5 MB，且能够在实际应用环境中以95%的定位准确率以及0.1 m的平均定位精度实现高精度定位。